Skip to main content
. 2025 Jul 1;16:1597030. doi: 10.3389/fpls.2025.1597030

Figure 1.

Flowchart illustrating emerging statistical techniques in nitric oxide research in plants. It highlights three categories: machine learning and predictive modeling, integration of omics data, and network analysis and systems biology. Subcategories include supervised and unsupervised learning techniques, deep learning, statistical and bioinformatics tools, gene regulatory networks, protein-protein interaction, metabolic network models, and modeling nitric oxide-dependent processes.

Overview of emerging statistical techniques in NO research. The figure illustrates the integration of machine learning models, multi-omics data analysis, and network analysis and systems biology approaches to uncover NO-mediated regulatory mechanisms in plants. (1) Machine learning techniques, including supervised learning (SVM, RF, ANN) and deep learning (CNN, RNN), predict plant responses to varying NO levels based on gene expression, environmental factors, and metabolic markers. (2) Integrative omics frameworks combine transcriptomics, proteomics, and metabolomics using statistical models such as WGCNA, Bayesian networks, and MOFA to identify key NO-regulated pathways. (3) Network-based systems biology approaches, including gene regulatory networks, protein-protein interaction networks, and metabolic pathway analysis, elucidate cross-talk between NO and other signaling molecules like ROS and phytohormones. Computational tools such as Cytoscape and STRING aid in network construction and visualization. These advanced methodologies enhance our understanding of NO signaling, enabling precise modeling of plant adaptation and stress responses.